Github user marmbrus commented on a diff in the pull request:
https://github.com/apache/spark/pull/6780#discussion_r32991598
--- Diff:
sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/InsertIntoHiveTable.scala
---
@@ -106,12 +103,16 @@ case class InsertIntoHiveTable(
}
writerContainer
- .getLocalFileWriter(row, table.schema)
- .write(serializer.serialize(outputData, standardOI))
+ .getLocalFileWriter(row, schema)
+ .write(newSer(fileSinkConf.getTableInfo).serialize(outputData,
standardOI))
}
writerContainer.close()
- }
+ }: Unit
+
+ writerContainer.driverSideSetup()
+ sc.sparkContext.runJob(rdd, sc.sparkContext.clean(writeToFile))
+ writerContainer.commitJob()
--- End diff --
It appears the change is breaking something in the serialization debugger.
```
15/06/22 22:25:41.020 main WARN SerializationDebugger: Exception in
serialization debugger
java.lang.reflect.InvocationTargetException
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at
org.apache.spark.serializer.SerializationDebugger$ObjectStreamClassMethods$.getObjFieldValues$extension(SerializationDebugger.scala:248)
at
org.apache.spark.serializer.SerializationDebugger$SerializationDebugger.visitSerializable(SerializationDebugger.scala:158)
at
org.apache.spark.serializer.SerializationDebugger$SerializationDebugger.visit(SerializationDebugger.scala:107)
at
org.apache.spark.serializer.SerializationDebugger$SerializationDebugger.visitSerializable(SerializationDebugger.scala:166)
at
org.apache.spark.serializer.SerializationDebugger$SerializationDebugger.visit(SerializationDebugger.scala:107)
at
org.apache.spark.serializer.SerializationDebugger$.find(SerializationDebugger.scala:66)
at
org.apache.spark.serializer.SerializationDebugger$.improveException(SerializationDebugger.scala:41)
at
org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:47)
at
org.apache.spark.serializer.JavaSerializerInstance.serialize(JavaSerializer.scala:81)
at
org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:319)
at
org.apache.spark.util.ClosureCleaner$.org$apache$spark$util$ClosureCleaner$$clean(ClosureCleaner.scala:312)
at
org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:139)
at org.apache.spark.SparkContext.clean(SparkContext.scala:1891)
at
org.apache.spark.sql.hive.execution.InsertIntoHiveTable.saveAsHiveFile(InsertIntoHiveTable.scala:114)
at
org.apache.spark.sql.hive.execution.InsertIntoHiveTable.sideEffectResult$lzycompute(InsertIntoHiveTable.scala:186)
at
org.apache.spark.sql.hive.execution.InsertIntoHiveTable.sideEffectResult(InsertIntoHiveTable.scala:125)
at
org.apache.spark.sql.hive.execution.InsertIntoHiveTable.doExecute(InsertIntoHiveTable.scala:263)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:89)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:89)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
at
org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:88)
at
org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:986)
at
org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:986)
at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:143)
at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:127)
at org.apache.spark.sql.DataFrame$.apply(DataFrame.scala:50)
at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:786)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:61)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:283)
at
org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:423)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:218)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at
org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:621)
at
org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:170)
at
org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:193)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:112)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.lang.ArrayIndexOutOfBoundsException: 0
at
java.io.ObjectStreamClass$FieldReflector.getObjFieldValues(ObjectStreamClass.java:2050)
at
java.io.ObjectStreamClass.getObjFieldValues(ObjectStreamClass.java:1252)
```
That said, it would be good if you could limit the changes in a given PR to
the task at hand, and do refactorings in a separate PR. It's okay when they
are very minor (i.e. fixing spelling), but grouping them together makes the PR
harder to review, harder to backport, and causes it to get blocked on unrelated
problems (such as this serialization issue).
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
